Related papers: SPLICE: A Singleton-Enhanced PipeLIne for Corefere…

The introduction of pretrained language models has reduced many complex task-specific NLP models to simple lightweight layers. An exception to this trend is coreference resolution, where a sophisticated task-specific model is appended to a…

CLIP's success has demonstrated that prompt tuning can achieve robust cross-modal semantic alignment for tasks ranging from open-domain recognition to fine-grained classification. However, redundant or weakly relevant feature components…

Character linking, the task of linking mentioned people in conversations to the real world, is crucial for understanding the conversations. For the efficiency of communication, humans often choose to use pronouns (e.g., "she") or normal…

We present a joint model for entity-level relation extraction from documents. In contrast to other approaches - which focus on local intra-sentence mention pairs and thus require annotations on mention level - our model operates on entity…

Coreference resolution systems are typically trained with heuristic loss functions that require careful tuning. In this paper we instead apply reinforcement learning to directly optimize a neural mention-ranking model for coreference…

Multimodal reference resolution, including phrase grounding, aims to understand the semantic relations between mentions and real-world objects. Phrase grounding between images and their captions is a well-established task. In contrast, for…

This paper presents an efficient speech enhancement (SE) approach that reuses a processing block repeatedly instead of conventional stacking. Rather than increasing the number of blocks for learning deep latent representations, repeating a…

We report here on a study of interannotator agreement in the coreference task as defined by the Message Understanding Conference (MUC-6 and MUC-7). Based on feedback from annotators, we clarified and simplified the annotation specification.…

Recent thinking models trained with reinforcement learning and backward-checking CoT often suffer from overthinking: they produce excessively long outputs even on simple problems, wasting computation. Existing evaluations, based on token…

Attention mechanisms, particularly softmax attention, have been instrumental in the success of transformer-based models such as GPT. However, the quadratic memory complexity of softmax attention with respect to sequence length poses…

Recent trends in semi-supervised learning have significantly boosted the performance of 3D semi-supervised medical image segmentation. Compared with 2D images, 3D medical volumes involve information from different directions, e.g.,…

Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs) to a stream of downstream tasks, but it suffers from catastrophic forgetting of earlier capabilities. Recent work shows that on-policy…

Coreference resolution, critical for identifying textual entities referencing the same entity, faces challenges in pronoun resolution, particularly identifying pronoun antecedents. Existing methods often treat pronoun resolution as a…

In sequence to sequence learning, the self-attention mechanism proves to be highly effective, and achieves significant improvements in many tasks. However, the self-attention mechanism is not without its own flaws. Although self-attention…

Few-Shot Instance Segmentation (FSIS) requires detecting and segmenting novel classes with limited support examples. Existing methods based on Region Proposal Networks (RPNs) face two issues: 1) Overfitting suppresses novel class objects;…

Point-based object localization (POL), which pursues high-performance object sensing under low-cost data annotation, has attracted increased attention. However, the point annotation mode inevitably introduces semantic variance due to the…

Recognizing coreferring events and entities across multiple texts is crucial for many NLP applications. Despite the task's importance, research focus was given mostly to within-document entity coreference, with rather little attention to…

Resolving pronoun coreference requires knowledge support, especially for particular domains (e.g., medicine). In this paper, we explore how to leverage different types of knowledge to better resolve pronoun coreference with a neural model.…

Large Language Models (LLMs) perform well on reasoning benchmarks but often fail when inputs alter slightly, raising concerns about the extent to which their success relies on memorization. This issue is especially acute in Chain-of-Thought…

The common practice in coreference resolution is to identify and evaluate the maximum span of mentions. The use of maximum spans tangles coreference evaluation with the challenges of mention boundary detection like prepositional phrase…